metadata

license: mit
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: xlnet-large-cased-ner-food-recipe-v2
    results: []

xlnet-large-cased-ner-food-recipe-v2

This model is a fine-tuned version of xlnet-large-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1036
Precision: 0.7976
Recall: 0.7874
F1: 0.7925
Accuracy: 0.9663

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-07
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.5	400	0.3117	0.3718	0.0264	0.0493	0.8933
0.4072	1.01	800	0.2093	0.7573	0.2371	0.3612	0.9160
0.2943	1.51	1200	0.1434	0.7922	0.6436	0.7102	0.9523
0.2159	2.01	1600	0.1269	0.7806	0.7091	0.7431	0.9581
0.1737	2.51	2000	0.1183	0.7974	0.7365	0.7657	0.9610
0.1737	3.02	2400	0.1111	0.8044	0.7674	0.7855	0.9638
0.1483	3.52	2800	0.1076	0.8085	0.7765	0.7922	0.9653
0.1423	4.02	3200	0.1051	0.8061	0.7797	0.7927	0.9658
0.1385	4.52	3600	0.1036	0.7976	0.7874	0.7925	0.9663

Framework versions

Transformers 4.27.4
Pytorch 2.0.0+cu118
Datasets 2.11.0
Tokenizers 0.13.3